analyze-task

analyze-task is a skill for Claude Code from AMAP-ML/LongHorizon-Harness. It costs 44 tokens per session (186 once invoked), scanned A, original, MIT.

A checker for OSWorld tasks, which are computer-use tasks evaluated by whether an instruction was completed correctly. It examines the task setup and evaluation method, then writes Markdown and JSON reports.

In plain words
What is it for?
Use it to validate one or more OSWorld task instructions, inspect visible setup files when needed, check the evaluation function, and save reports for each task.
Why use it?
It identifies whether a task can be completed and judged fairly before an agent attempts it.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

Good fit Use it to validate one or more OSWorld task instructions, inspect visible setup files when needed, check the evaluation function, and save reports for each task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/amap-ml/longhorizon-harness/analyze-task
About the project

LongHorizon-Harness is a computer-use harness that lets AI agents continue work across desktop applications and the command line for extended periods by planning, acting, verifying, checkpointing, and recovering. It is for users who need Claude Code, Codex, OpenCode, or DeepSeek Harness to make reliable progress on complex long-running workflows without training a new model. The catalogue entries provide skills for operating this execution loop.

AMAP-ML/LongHorizon-Harness · 1,481 stars · on GitHub · lh-harness.pages.dev

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add AMAP-ML/LongHorizon-Harness --skill analyze-task
Clone the repo
git clone --depth 1 https://github.com/AMAP-ML/LongHorizon-Harness

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for analyze-task

README.md
[![agentmods](https://agentmods.dev/badge/skills/amap-ml/longhorizon-harness/analyze-task/github.svg)](https://agentmods.dev/skills/amap-ml/longhorizon-harness/analyze-task)
Your own site
<a href="https://agentmods.dev/skills/amap-ml/longhorizon-harness/analyze-task"><img src="https://agentmods.dev/badge/skills/amap-ml/longhorizon-harness/analyze-task/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for analyze-task

Your own site · 80×15
<a href="https://agentmods.dev/skills/amap-ml/longhorizon-harness/analyze-task"><img src="https://agentmods.dev/badge/skills/amap-ml/longhorizon-harness/analyze-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 186 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.00186
Opus 5 $0.00022 $0.00093
Sonnet 5 $0.00009 $0.00037
Haiku 4.5 $0.00004 $0.00019

Measured 10d ago against content hash 7036bd90775d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

analyze-task scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

eval/OSWorldv2-harness/OSWorld-V2/.claude/skills/analyze-task/SKILL.md · 11 lines

What it actually says

If only one task is issued, analyze it directly with instruction: analyze-single-task.md.

If multiple tasks are issued, use subagents to analyze them in parallel (one agent for each task) and save reports under check/<task_id>/. Do not analyze them sequentially by yourself. DO NOT tell it what to do. Just ask the subagent to analyze the task in target directory and use this skill (analyze-task) to do the analysis. Pass any user instructions to every subagent.

After the subagents finish, do nothing but report to user that the check is done and where to find the reports.

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 11 lines · 44 tokens per session scan A 7036bd90775d

Subscribe to this mod's changes

analyze-task is a skill published in the GitHub repository AMAP-ML/LongHorizon-Harness (1,481 stars, last pushed 20d ago), licensed MIT. It adds 44 tokens to every session and 186 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.